Embedded real-time stereo estimation via Semi-Global Matching on the GPU

D. Hernandez-Juarez, A. Chacon, A. Espinosa, D. Vazquez, J. C. Moure, A. M. Lopez

Producció científica: Contribució a una revistaArticleRecercaAvaluat per experts

137 Cites (Scopus)


Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energye cient GPU devices. Our design runs on a Tegra X1 at 42 frames per second (fps) for an image size of 640 480, 128 disparity levels, and using 4 path directions for the SGM method.

Idioma originalEnglish
Pàgines (de-a)143-153
Nombre de pàgines11
RevistaProcedia Computer Science
Estat de la publicacióPublicada - 2016


Navegar pels temes de recerca de 'Embedded real-time stereo estimation via Semi-Global Matching on the GPU'. Junts formen un fingerprint únic.

Com citar-ho